Photo by Vitaly Gariev on Unsplash
Engineering project
AI extraction of financial data
Extract information from financial announcements and integrate it into a data platform as structured data.
The project
AI processing of financial announcements at an international index provider. This implementation connects document analysis to a data platform and a production workflow.
Engineering approach
The model works on document content, while the data platform holds the structured information produced. This separation gives versioned instructions and integration processing distinct roles. The reference view places extraction within a wider analytical pipeline.
Work delivered
Financial-data extraction processing used in production.
My contribution
- Extraction of data from financial announcements using Vertex AI
- Integration of structured information with the BigQuery environment
- Versioning of the instructions used for extraction processing
Related reference architecture
A Google Cloud platform brings market feeds and information extracted from financial documents into a BigQuery warehouse. One application is building a history of financial instruments and portfolios for analysis in Power BI and use by applications through APIs.
Apache Airflow
BigQuery
Cloud Run
Cloud Storage
dbt
GitHub
Power BI
Terraform
Vertex AI
Components and flows
- Source files retained in Cloud Storage and loaded into raw BigQuery tables
- dbt transformations and data quality checks before publishing fact and dimension tables
- Document extraction through Vertex AI, analysis in Power BI and application access through Cloud Run APIs
Discuss your project
A discussion of your project’s design, development and production deployment.